Bezczynny

Twoje żądanie będzie kosztować $0.06 za uruchomienie.
Za $1 możesz uruchomić ten model w przybliżeniu 16 razy.
Jeszcze jedna rzecz:

OpenAI GPT Image 2 Edit transforms one or more reference images using natural-language instructions. Upload your image, describe the changes you want, and the model generates a polished edited result with strong prompt alignment and production-ready quality.
Natural-language image editing Edit images by simply describing the changes you want in plain language — no manual masking or complex editing workflow required.
Works with reference images Use one or more input images as the visual source for edits, transformations, or style adjustments.
Flexible aspect ratios Generate edited outputs in square, portrait, or landscape formats for different publishing and design needs.
Production-ready API Access the model through a ready-to-use REST inference API for easy integration into apps, tools, and creative pipelines.
Fast and affordable Get high-quality image edits with simple usage-based pricing and no cold-start friction.
| Parameter | Required | Description |
|---|---|---|
| images | Yes | Reference images to edit |
| prompt | Yes | Text description of the desired edit |
| aspect_ratio | No | Aspect ratio: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. Auto-detected from input image if not specified. |
| resolution | No | Output resolution: 1k (default), 2k, or 4k. |
| quality | No | Image quality: low, medium (default), or high. |
1:1 for square, 2:3 or 9:16 for portrait, 3:2 or 16:9 for landscape, etc. Auto-detected from input image if not specified.Turn this product photo into a premium studio advertisement with soft cinematic lighting, a clean beige background, subtle shadows, realistic reflections, and luxury brand aesthetics
Pricing varies by quality and resolution.
| Quality | 1k | 2k | 4k |
|---|---|---|---|
| low | $0.030 | $0.060 | $0.090 |
| medium | $0.060 | $0.120 | $0.180 |
| high | $0.220 | $0.440 | $0.660 |
images and prompt are required fields.1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9. Auto-detected from input image if not specified.